Publications and code

• Ben-Iwhiwhu, E., Nath, S., Pilly, P.K., Kolouri, S. and Soltoggio, A., 2022. Lifelong Reinforcement Learning with Modulating Masks. arXiv preprint arXiv:2212.11110.
• Soltoggio, A., Ben-Iwhiwhu, E., Peridis, C., Ladosz, P., Dick, J., Pilly, P.K. and Kolouri, S., 2023. The configurable tree graph (CT-graph): measurable problems in partially observable and distal reward environments for lifelong reinforcement learning. arXiv preprint arXiv:2302.10887.
• Liu, X., Bai, Y., Lu, Y., Soltoggio, A. and Kolouri, S., 2022. Wasserstein Task Embedding for Measuring Task Similarities. arXiv preprint arXiv:2208.11726.
• Yuzhe Lu, Xinran Liu, Andrea Soltoggio, Soheil Kolouri: SLOSH: Set LOcality Sensitive Hashing via Sliced-Wasserstein Embeddings Dec 2021</li>
• Loughborough University press release, Sep 2021
• Azorobotics: New project hopes to make independent AI systems to learn from each other, Sep 2021

  Code

  • The ShELL agent This is the code to lauch a ShELL collective of agents.
  • The configurable tree graph (CT-graph) is a lightweight RL environment for a range of challenging lifelong learning scenarios.
  • The dynamic grid is a lightweight RL environment to real task variation in the input domain, MDP transion change and reward function changes.